Deep Learning and Artificial Intelligence are the new frontier - machine learning systems that not only learn from data, but even learn what is really important in the data. From self-driving cars to smart speakers like Alexa, deep learning is bringing the future to us.
TensorFlow is an open source software library released by Google in 2015 to make it easier for developers to design, build, and train deep learning models. TensorFlow originated as an internal library that Google developers used to build machine learning models in-house but today, Tensorflow is popular the world over because of how easy and intuitive it is to use.
This course starts from first principles. It assumes no prior knowledge of Tensorflow, all you need to know is basic Python programming.
We start off by understanding the anatomy of a simple Tensorflow program, and basic constructs such as graphs, tensors, constants, placeholders, and sessions. We then build regression models in Tensorflow. This covers both linear and logistic regression and introduces the estimator API. The estimator API in Tensorflow is a simple high-level API which makes building and evaluating models very simple.
We then move on to the cool stuff, neural networks. We'll understand the function of a single neuron and how layers of neurons come together to do some pretty magical stuff. We'll build both classification and regression models using deep neural networks.
